Texas Instruments Corporation

Chaitanya Satish Ghone

Mihir Narendra Mody

Minhua Zhou

Manu Mathew

Ranga Ramanujam Srinivasan

Joseph Meehan

Veeramanikandan Raju

Deepak Kumar Poddar

Niraj Nandan

Hetul Sanghvi

Dipan Kumar Mandal

Mahesh Madhukar Mehendale

Piyali Goswami

Naresh Kumar Yadav

A video decoder system, in one embodiment, includes one or more processors and a memory storing instructions that when executed by the one or more processors cause the video decoding system to perform an entropy decoding operation in a frame level pipelined manner on a bitstream representative of encoded video data to produce first output data, perform at least one of an inverse quantization operation or an inverse frequency transform operation in a row level pipelined manner on the first output data to produce second output data, perform a deblocking filtering operation on first input data that includes the second output data in a row level pipelined manner to produce third output data, and output a decoded video output based on the third output data.

High definition VP8 decoder

A method is provided that includes receiving pictures of a video sequence in a video encoder, and encoding the pictures to generate a compressed video bit stream that is transmitted to a video decoder in real-time, wherein encoding the pictures includes selecting a picture to be encoded as a delayed duplicate intra-predicted picture (DDI), wherein the picture would otherwise be encoded as an inter-predicted picture (P-picture), encoding the picture as an intra-predicted picture (I-picture) to generate the DDI, wherein the I-picture is reconstructed and stored for use as a reference picture for a decoder refresh picture, transmitting the DDI to the video decoder in non-real time, selecting a subsequent picture to be encoded as the decoder refresh picture, and encoding the subsequent picture in the compressed bit stream as the decoder refresh picture, wherein the subsequent P-picture is encoded as a P-picture predicted using the reference picture.

Delayed duplicate I-picture for video coding

A convolutional neural network (CNN)-based signal processing includes receiving of an encrypted output from a first layer of a multi-layer CNN data. The received encrypted output is subsequently decrypted to form a decrypted input to a second layer of the multi-layer CNN data. A convolution of the decrypted input with a corresponding decrypted weight may generate a second layer output, which may be encrypted and used as an encrypted input to a third layer of the multi-layer CNN data.

Secure convolutional neural networks (CNN) accelerator

A method for analyzing images to generate a plurality of output features includes receiving input features of the image and performing Fourier transforms on each input feature. Kernels having coefficients of a plurality of trained features are received and on-the-fly Fourier transforms (OTF-FTs) are performed on the coefficients in the kernels. The output of each Fourier transform and each OTF-FT are multiplied together to generate a plurality of products and each of the products are added to produce one sum for each output feature. Two-dimensional inverse Fourier transforms are performed on each sum.

Methods and systems for analyzing images in convolutional neural networks

A Convolutional Neural Network (CNN) based-signal processing includes receiving of an encrypted output from a first layer of a multi-layer CNN data. The received encrypted output is subsequently decrypted to form a decrypted input to a second layer of the multi-layer CNN data. A convolution of the decrypted input with a corresponding decrypted weight may generate a second layer output, which may be encrypted and used as an encrypted input to a third layer of the multi-layer CNN data.

A control processor for a video encode-decode engine is provided that includes an instruction pipeline. The instruction pipeline includes an instruction fetch stage coupled to an instruction memory to fetch instructions, an instruction decoding stage coupled to the instruction fetch stage to receive the fetched instructions, and an execution stage coupled to the instruction decoding stage to receive and execute decoded instructions. The instruction decoding stage and the instruction execution stage are configured to decode and execute a set of instructions in an instruction set of the control processor that are designed specifically for accelerating video sequence encoding and encoded video bit stream decoding.

Processor instructions for accelerating video coding

A VP8 video decoder is implemented by partitioning the required functions across multiple sub systems, with an optimal mapping to existing functional blocks. Key optimizations include the reuse of hardware designed for prior generation VP6 and VP7 decoders. In order to reduce implementation complexity, cost and power consumption, a non-exact, approximate deblocking loop filter is implemented.

A VP8 video decoder is implemented by partitioning the required functions across multiple sub systems, with an optimal mapping to existing functional blocks. Key optimizations include the reuse of hardware designed for prior generation V^6 and VP7 decoders. In order to reduce implementation complexity, cost and power consumption, a non exact, approximate deblocking loop filter is implemented.

Growing community of inventors

Pune, India

Chaitanya Satish Ghone